© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 32601
    Prev
    Next
    INDEX
    Explanations

    phrases related to the construction and proof of mathematical concepts or algorithms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    tagHelperRunner
    -0.85
     ostavi
    -0.82
     SafeMath
    -0.81
     мәкал
    -0.78
    richTextPanel
    -0.76
    expandindo
    -0.72
    addPreferredGap
    -0.71
    endphp
    -0.70
    __":
    -0.68
     >=",
    -0.68
    POSITIVE LOGITS
     selamat
    0.48
    NameValuePair
    0.45
    listdir
    0.45
     rule
    0.42
     Offic
    0.42
     enumerate
    0.41
     reafon
    0.41
    וי
    0.41
     offici
    0.41
    WithTag
    0.41
    Activations Density 0.067%

    No Known Activations